Value of C-reactive protein/albumin ratio in predicting intravenous immunoglobulin-resistant Kawasaki disease- a data from multi-institutional study in China

Construction and validation of predictive models for intravenous immunoglobulin-resistant Kawasaki disease using an interpretable machine learning approach

BACKGROUND

Intravenous immunoglobulin (IVIG)-resistant Kawasaki disease is associated with coronary artery lesion development.

PURPOSE

This study aimed to explore the factors associated with IVIG-resistance and construct and validate an interpretable machine learning (ML) prediction model in clinical practice.

METHODS

Between December 2014 and November 2022, 602 patients were screened and risk factors for IVIG-resistance investigated. Five ML models are used to establish an optimal prediction model. The SHapley Additive exPlanations (SHAP) method was used to interpret the ML model.

RESULTS

Na+, hemoglobin (Hb), C-reactive protein (CRP), and globulin were independent risk factors for IVIG-resistance. A nonlinear relationship was identified between globulin level and IVIG-resistance. The XGBoost model exhibited excellent performance, with an area under the receiver operating characteristic curve of 0.821, accuracy of 0.748, sensitivity of 0.889, and specificity of 0.683 in the testing set. The XGBoost model was interpreted globally and locally using the SHAP method.

CONCLUSION

Na+, Hb, CRP, and globulin levels were independently associated with IVIG-resistance. Our findings demonstrate that ML models can reliably predict IVIG-resistance. Moreover, use of the SHAP method to interpret the established XGBoost model's findings would provide evidence of IVIG-resistance and guide the individualized treatment of Kawasaki disease.

Neutrophil percentage-to-albumin ratio is a potential marker of intravenous immunoglobulin resistance in Kawasaki disease

Intravenous immunoglobulin (IVIG) resistance in Kawasaki disease (KD) was associated with coronary artery lesions. Neutrophil percentage-to-albumin ratio (NPAR) is an index of mortality in several inflammatory diseases. This study focused on the association of NPAR with IVIG- resistance in KD. Clinical and laboratory data of 438 children with KD before IVIG treatment were retrospectively analyzed. Notably, high NPAR was associated with older age, high WBC, NP, ALT, total bilirubin and CRP, as well as with high the incidence of IVIG-resistance, and with low hemoglobin (Hb), PLT, ALB and sodium levels. NPAR (OR: 2.366, 95% CI: 1.46-3.897, p = 0.001) and Hb (OR: 0.967, 95% CI: 0.944-0.989, p = 0.004) were independent risk factors for IVIG-resistance. NPAR showed linear relation with IVIG-resistance (p for nonlinear = 0.711) and the nonlinear correlation was found between IVIG-resistance and Hb (p for nonlinear = 0.002). The predictive performance of NPAR was superior to Beijing model (z = 2.193, p = 0.028), and not inferior to Chongqing model (z = 0.983, p = 0.326) and the combination of NPAR and Hb (z = 1.912, p = 0.056). These findings revealed that NPAR is a reliable predictor of IVIG-resistance.

C-reactive protein to albumin ratio as a prognostic tool for predicting intravenous immunoglobulin resistance in children with kawasaki disease: a systematic review of cohort studies

BACKGROUND

Intravenous immunoglobulin (IVIG) is the primary treatment for Kawasaki disease (KD). However, 10-20% of KD patients show no response to IVIG treatment, making the early prediction of IVIG resistance a key focus of KD research. Our aim is to explore the application of the C-reactive protein to albumin ratio (CAR) for predicting IVIG resistance in children with KD through meta-analysis.

METHODS

Cochrane Library, PubMed, MEDLINE, EMbase, CNKI, WanFang, the Chinese Biomedical Database, and CQVIP were searched up to November 2023 for cohort studies on predicting IVIG-resistant KD using the CAR. Articles were selected based on pre-established inclusion and exclusion criteria after extracting literature data and assessing them using the QUADAS-2.0 tool for evaluating the accuracy of diagnostic tests. Stata 15.0 software was used for meta-analysis.

RESULTS

Four Chinese and English literature reports were included in this meta-analysis. The results revealed the presence of a threshold effect and high heterogeneity among the included studies. The combined sensitivity for CAR predicting IVIG-resistant KD was calculated as 0.65 (95% CI 0.58-0.72), specificity as 0.71 (95% CI 0.57-0.81), and the area under the curve (AUC) as 0.70 (95% CI 0.66-0.74) using the random-effects model. The combined positive likelihood ratio was 2.22 (95% CI 1.35-3.65), the combined negative likelihood ratio was 0.49 (95% CI 0.35-0.69), and the diagnostic odds ratio was 5 (95% CI 2-10).

CONCLUSION

CAR is an auxiliary predictive indicator with moderate diagnostic value that provides guidance in the early treatment of the disease, demonstrating a certain predictive value that warrants further investigation. However, CAR cannot yet be considered as a definitive diagnostic or exclusionary marker for IVIG-resistant KD. Therefore, multi-center, large sample, and high-quality long-term follow-up trials are warranted to confirm the current findings.

Prognostic Nutritional Index Enhances the Discriminatory Ability of Procalcitonin for Predicting Pediatric Sepsis

Objective. Improving diagnostic ability of pediatric sepsis is of great significance for reducing the mortality of sepsis. This study explored the discriminatory capacity of nutritional index (PNI) in pediatric sepsis. Methods. We retrospectively enrolled 134 children with suspected sepsis and collected their clinical and laboratory data. Receiver operating characteristic curves (ROC), decision curve analysis (DCA) and net reclassification improvement (NRI) were performed to compare the predictive significance of the PNI, procalcitonin (PCT) and their combination. Results. Among 134 patients, 65 children were diagnosed with sepsis and 69 children with non-sepsis. PCT and PNI were independently associated with pediatric sepsis. PCT was superior to PNI to predict pediatric sepsis. The model based on PCT + PNI improved the predictive capacity than them alone, as demonstrated by ROC, DCA and NRI, respectively. Conclusion. PNI was independently associated with pediatric sepsis, and addition of PNI could improve the capacity of PCT to predict pediatric sepsis.

Serum IL-41 might be a biomarker for IVIG resistance and coronary artery lesions in Kawasaki disease

BACKGROUND

This study aimed to evaluate serum IL-41 levels in IVIG resistance and CALs, and to elucidate the relationship between IL-41 and Kawasaki disease (KD)-related clinical parameters.

METHODS

93 children with KD were collected. Baseline clinical data were obtained by physical examination. Serum IL-41 levels were detected with an enzyme-linked immunosorbent assay. The correlations between IL-41 and the clinical parameter of KD were performed by Spearman correlation coefficient. Receiver operating characteristic curve analysis was performed to assess the predictive ability of IL-41 for IVIG resistance and CALs.

RESULTS

Serum IL-41 levels were significantly increased in the IVIG resistance group compared with the response group, and serum IL-41 levels in the CALs group were higher than those in the non-CALs group. Serum IL-41 levels were positively correlated with erythrocyte sedimentation rate, C-reactive protein and C-reactive protein/albumin ratio, but negatively correlated with albumin. Serum IL-41 levels was an independent risk factor for CALs, and total fever days and neutrophil-to-lymphocyte ratio (NLR) were independent predictors for IVIG resistance. The area under the curve (AUC) value for serum IL-41 to predict IVIG resistance was 0.73, yielding a sensitivity of 54.55% and a specificity of 81.71%. The AUC of serum IL-41 was 0.712, with a sensitivity of 63.16% and a specificity of 72.97% for predicting CALs. IL-41 was not inferior to NLR in predicting IVIG resistance (z = 0.282, p = 0.7783).

CONCLUSIONS

Serum IL-41 was increased in IVIG resistance and CALs. Serum IL-41 might be a new potential biomarker for IVIG resistance and CALs.

The role of indices in predicting disease severity and outcomes of multisystem inflammatory syndrome in children

BACKGROUND

The aim of this study was to evaluate the role of the systemic immune inflammation index (SII), C-reactive protein/albumin ratio (CAR), the monocyte/lymphocyte ratio (MLR), and the neutrophil/lymphocyte ratio (NLR) in predicting disease severity, treatment, and prognosis in multisystem inflammatory syndrome in children (MIS-C).

METHODS

This medical record review retrospectively evaluated the clinical and laboratory findings of 191 MIS-C patients followed in the Department of Pediatric Rheumatology at Ankara City Hospital, Turkey. The patients were grouped by disease severity: mild, moderate, and severe. SII, CAR, MLR, and NLR were calculated for each group.

RESULTS

All patients had fever at the time of admission; 153 (80.1%) had gastrointestinal tract involvement, 74 (38.7%) had rash, 63 (33%) had conjunctivitis, 107 (56%) had cardiac involvement, 32 (15.6%) had renal involvement, and 143 (74.9%) had hematological involvement. According to logistic regression analysis, SII, NLR, MLR, and CAR were found to be predictive indexes for disease severity, need for intensive care, need for inotropes, and anakinra treatment in MIS-C. The cut-off values of ≥1605.3 for SII, ≥9.1 for NLR, and ≥3.9 for CAR increased the risk of severe disease by 3.4, 7.1, and 5.7 times, respectively.

CONCLUSION

NLR, SII, MLR, and CAR are effective and useful for predicting the severity of MIS-C, the need for intensive care, and the need for anakinra treatment.

The Prognostic Significance of C-Reactive Protein to Albumin Ratio in Patients With Severe Fever With Thrombocytopenia Syndrome

Background

Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease with the high case-fatality rate, lacking effective therapies and vaccines. Inflammation-based indexes have been widely used to predict the prognosis of patients with cancers and some inflammatory diseases. In our study, we aim to explore the predictive value of the inflammation-based indexes in SFTS patients.

Methods

We retrospectively analyzed 82 patients diagnosed with SFTS. The inflammation-based indexes, including neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII), systemic inflammation response index (SIRI), aggregate index of systemic inflammation (AISI) and C-reactive protein to albumin ratio (CAR), were compared between the survival and death patients. Receiver operating characteristic (ROC) curves were used to compare the predictive ability of MLR, AISI, and CAR. The survival analysis was based on the Kaplan–Meier (KM) method. Multivariate logistic regression analysis was used to analyze the independent risk factors of poor prognosis in patients with SFTS.

Results

The CAR is higher in the death group while MLR and AISI were higher in the survival group. The ROC curve analysis indicated CAR exhibited more predictive value than the other indexes and the optimal cut-off value of CAR was equal to or greater than 0.14. KM survival curve showed that higher CAR was significantly correlated to the lower overall survival in SFTS patients. Multivariate logistic regression analysis indicated that CAR was an independent risk factor for poor prognosis in patients with SFTS.

Conclusion

The CAR is an independent risk factor for death in patients with SFTS and could predict the poor prognosis of SFTS patients. It could be used as a biomarker to help physicians to monitor and treat patients more aggressively to improve clinical prognosis.

Value of blood inflammatory markers for predicting intravenous immunoglobulin resistance in Kawasaki disease: A systematic review and meta-analysis

BACKGROUND

Previous studies have assessed the diagnostic accuracy of blood inflammatory markers like neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and C-reactive protein (CRP), and CRP to albumin ratio (CAR) to predict the resistant Kawasaki disease (KD). The aim of the current meta-analysis and systematic review is to compare the prognostic ability of these inflammatory markers to predict the resistance to IVIG in patients with Kawasaki disease.

METHODS

A systematic search of online academic databases and search engines such as EMBASE, PubMed Central, MEDLINE, Cochrane library, Google Scholar, and ScienceDirect was conducted for papers that report the diagnostic accuracy of inflammatory markers for resistant KD. Meta-analysis was performed using STATA software.

RESULTS

Twenty-two studies met the inclusion criteria. Pooled sensitivity and specificity of NLR as a predictor of resistant Kawasaki disease was 72% (95% CI: 62%, 80%) and 71% (95% CI: 63%, 78%), with AUC of 0.77 for PLR was 60% (95% CI: 50%, 69%) and 68% (95% CI: 61%, 75%), with area under the curve (AUC) of 0.69. Pooled sensitivity and specificity of CRP was 75% (95% CI: 68%, 81%) and 66% (95% CI: 55%, 76%), respectively, with an AUC value of 0.78. Pooled sensitivity and specificity of combined NLR and PLR was 58% (95% CI: 46%, 69%) and 73% (95% CI: 65%, 79%), respectively, with an AUC value of 0.72.

CONCLUSION

Our study found that NLR, CRP, PLR, and combined NLR/PLR have a good prognostic value in patients with resistant Kawasaki disease, with moderate to high sensitivity and specificity. More research on the accuracy of these indexes in multiple combinations is needed.

SYSTEMATIC REVIEW REGISTRATION

[https://www.crd.york.ac.uk/prospero/], identifier [CRD42022322165].

Early Prediction of Disease Progression in Patients with Severe COVID-19 Using C-Reactive Protein to Albumin Ratio

Background

Early identification of patients with severe coronavirus disease (COVID-19) at an increased risk of progression may promote more individualized treatment schemes and optimize the use of medical resources. This study is aimed at investigating the utility of the C-reactive protein to albumin (CRP/Alb) ratio for early risk stratification of patients.

Methods

We retrospectively reviewed 557 patients with COVID-19 with confirmed outcomes (discharged or deceased) admitted to the West Court of Union Hospital, Wuhan, China, between January 29, 2020 and April 8, 2020. Patients with severe COVID-19 (n = 465) were divided into stable (n = 409) and progressive (n = 56) groups according to whether they progressed to critical illness or death during hospitalization. To predict disease progression, the CRP/Alb ratio was evaluated on admission.

Results

The levels of new biomarkers, including neutrophil-to-lymphocyte ratio, platelet-to-lymphocyte ratio, CRP/Alb ratio, and systemic immune-inflammation index, were higher in patients with progressive disease than in those with stable disease. Correlation analysis showed that the CRP/Alb ratio had the strongest positive correlation with the sequential organ failure assessment score and length of hospital stay in survivors. Multivariate logistic regression analysis showed that percutaneous oxygen saturation (SpO2), D-dimer levels, and the CRP/Alb ratio were risk factors for disease progression. To predict clinical progression, the areas under the receiver operating characteristic curves of Alb, CRP, CRP/Alb ratio, SpO2, and D-dimer were 0.769, 0.838, 0.866, 0.107, and 0.748, respectively. Moreover, patients with a high CRP/Alb ratio (≥1.843) had a markedly higher rate of clinical deterioration (log − rank p < 0.001). A higher CRP/Alb ratio (≥1.843) was also closely associated with higher rates of hospital mortality, ICU admission, invasive mechanical ventilation, and a longer hospital stay.

Conclusion

The CRP/Alb ratio can predict the risk of progression to critical disease or death early, providing a promising prognostic biomarker for risk stratification and clinical management of patients with severe COVID-19.